src/morzhol-strings.adb

   1 ------------------------------------------------------------------------------
   2 --                                Morzhol                                   --
   3 --                                                                          --
   4 --                         Copyright (C) 2007-2008                          --
   5 --                      Pascal Obry - Olivier Ramonat                       --
   6 --                                                                          --
   7 --  This library is free software; you can redistribute it and/or modify    --
   8 --  it under the terms of the GNU General Public License as published by    --
   9 --  the Free Software Foundation; either version 2 of the License, or (at   --
  10 --  your option) any later version.                                         --
  11 --                                                                          --
  12 --  This library is distributed in the hope that it will be useful, but     --
  13 --  WITHOUT ANY WARRANTY; without even the implied warranty of              --
  14 --  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU       --
  15 --  General Public License for more details.                                --
  16 --                                                                          --
  17 --  You should have received a copy of the GNU General Public License       --
  18 --  along with this library; if not, write to the Free Software Foundation, --
  19 --  Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA.       --
  20 ------------------------------------------------------------------------------
  21
  22 package body Morzhol.Strings is
  23
  24    ------------------
  25    -- HTML_To_Text --
  26    ------------------
  27
  28    function HTML_To_Text (HTML_Source : in String) return String is
  29
  30       subtype Source_Range is Positive range HTML_Source'Range;
  31
  32       Result  : Unbounded_String;
  33       Last    : Integer := HTML_Source'First;
  34       To_Skip : Natural := 0;
  35
  36       procedure Find_End_Tag (Position : in Source_Range);
  37       --  Find end tag
  38
  39       ------------------
  40       -- Find_End_Tag --
  41       ------------------
  42
  43       procedure Find_End_Tag (Position : in Source_Range) is
  44       begin
  45          for L in Position + 1 .. HTML_Source'Last loop
  46             if HTML_Source (L) = '>' then
  47                To_Skip := L - Position;
  48                Last    := L + 1;
  49                return;
  50             end if;
  51          end loop;
  52       end Find_End_Tag;
  53
  54    begin
  55       Skip_HTML_Tag :
  56       for K in HTML_Source'Range loop
  57          if To_Skip /= 0 then
  58             To_Skip := To_Skip - 1;
  59
  60          else
  61             if HTML_Source (K) = '<' then
  62                Append (Result, HTML_Source (Last .. K - 1));
  63                Find_End_Tag (K);
  64
  65                if To_Skip = 0 then
  66                   --  No last end tag
  67                   Last := HTML_Source'Last;
  68                end if;
  69             end if;
  70          end if;
  71       end loop Skip_HTML_Tag;
  72
  73       if Last < HTML_Source'Last then
  74          Append (Result, HTML_Source (Last .. HTML_Source'Last));
  75       end if;
  76
  77       return -Result;
  78    end HTML_To_Text;
  79
  80 end Morzhol.Strings;